Multi-person motion prediction is a challenging task, especially for
rea...
Retouching images is an essential aspect of enhancing the visual appeal ...
Recent attention in instance segmentation has focused on query-based mod...
Limited by the nature of the low-dimensional representational capacity o...
Automatic image colorization is a particularly challenging problem. Due ...
Leveraging StyleGAN's expressivity and its disentangled latent codes,
ex...
This paper introduces DCT-Net, a novel image translation architecture fo...
Semantic segmentation on driving-scene images is vital for autonomous
dr...
Video frame interpolation (VFI) aims to improve the temporal resolution ...
Body reshaping is an important procedure in portrait photo retouching. D...
Noisy labels are commonly found in real-world data, which cause performa...
Image inpainting aims to complete the missing or corrupted regions of im...
Accurate lighting estimation is challenging yet critical to many compute...
Despite the great success of GANs in images translation with different
c...
Different from general photo retouching tasks, portrait photo retouching...
Blind face restoration (BFR) from severely degraded face images in the w...
Image inpainting is an underdetermined inverse problem, it naturally all...
The existence of noisy labels in real-world data negatively impacts the
...
Lighting estimation from a single image is an essential yet challenging ...
This paper proposes a novel active boundary loss for semantic segmentati...
Illumination estimation from a single image is critical in 3D rendering ...
Dealing with the inconsistency between a foreground object and a backgro...
Recent advances in generative adversarial networks (GANs) have achieved ...
The ability to produce convincing textural details is essential for the
...
Semantic human matting aims to estimate the per-pixel opacity of the
for...
Video contents have become a critical tool for promoting products in
E-c...
The identification of pulmonary lobes is of great importance in disease
...
Neural style transfer has drawn considerable attention from both academi...